论文笔记:Deep Algorithm Unrolling for Blind Image Deblurring

这是一篇CVPR2020的去模糊论文,主要是通过传统与深度相结合,将迭代次数变成神经网络的层数,使网络结构的网络结构更加具有解释性。

主要贡献: 

Deep Unrolling for Blind Image Deblurring (DUBLID):提出一种可解释的神经网络结构叫做DUBLID,首先提出一种迭代算法,该算法被认为是梯度域中传统的广义全变分正则方法(generalized TV-regularized algorithm)的推广。   

       算法步骤的每次迭代都表示为网络的一层,连接这些层形成一个深层神经网络。通过网络相当于执行有限次数的迭代算法。此外,算法参数(例如模型参数和正则化系数)转移到网络参数。可以使用反向传播来训练网络,从而产生从真实世界训练集中学习的模型参数。这样,训练后的网络可以自然地解释为参数优化算法,有效地克服了大多数传统神经网络缺乏可解释性的问题。传统的迭代算法与流行的神经网络相比通常需要的参数更少。因此,展开的网络具有很高的参数效率,并且需要较少的训练数据。此外,展开的网络自然继承了先前的结构和领域知识,而不是从密集的训练数据中学习它们。因此,它们倾向于比一般网络更好地推广,并且只要每次算法迭代(或相应的层)不太昂贵,计算速度就会更快。

        算法展开的概述:给定迭代算法(左),可以通过级联其迭代h来生成相应的深层网络(右)。迭代步骤h(左)被执行多次,生成网络层h1、h2…(右)。每次迭代h取决于算法参数θ,这些参数被转换成网络参数θ1、θ2...我们学习θ1、θ2…,而不是通过交叉验证或分析推导来确定这些参数,从训练数据集到端到端训练。这样,最终得到的网络可以获得比原始迭代算法更好的性能。

网络结构如下图:

半二次分裂方法(HQS):一般是将正则项中的原始变量进行变量替换,然后增加拉格朗日乘子项和二次惩罚项,这么做的目的是,去耦合的同时,简化计算。

基于半二次分裂方法(HQS)解决梯度域去模糊,开发了一个新的迭代优化展开算法。

线性核训练数据集:Berkeley Segmentation Data Set 500 (BSDS500)【是一个边缘检测数据集】

非线性核数据集:Microsoft COCO dataset 【是一个物体检测、分割和字幕数据集】

使用级联3×3小滤波器代替大滤波器,降低了参数的维度,并且网络可以更容易训练,

模糊的图像是通过将清晰的图像与模糊内核进行卷积合成,还添加了高斯白噪声(标准差为0.01)

这个方法用在作者自己所创造的数据集里效果还不错,但是真实的模糊图像不会这么简单,作者也提出在GO_PRO训练集中效果不是很好,代码还未开源。

菜鸡一枚,暂时理解就这么多,有错误请指正哈

 

 

 

  • 3
    点赞
  • 8
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
【作 者】Per Christian Hansen 【出版社】Society for Industrial and Applied Mathematic 【出版日期】October 29, 2006 【ISBN】0898716187 9780898716184 【形态项】9.8 x 6.7 x 0.3 inches 【语 言】English 【价 格】$63.00 Deblurring Images: Matrices, Spectra, and Filtering (Fundamentals of Algorithms 3) (Fundamentals of Algorithms) By Per Christian Hansen Publisher: Society for Industrial and Applied Mathematic Number Of Pages: 130 Publication Date: 2006-10-29 ISBN-10 / ASIN: 0898716187 ISBN-13 / EAN: 9780898716184 Binding: Paperback “The book’s focus on imaging problems is very unique among the competing books on inverse and ill-posed problems. …It gives a nice introduction into the MATLAB world of images and deblurring problems.” — Martin Hanke, Professor, Institut für Mathematik, Johannes-Gutenberg-Universität. When we use a camera, we want the recorded image to be a faithful representation of the scene that we see, but every image is more or less blurry. In image deblurring, the goal is to recover the original, sharp image by using a mathematical model of the blurring process. The key issue is that some information on the lost details is indeed present in the blurred image, but this “hidden” information can be recovered only if we know the details of the blurring process. Deblurring Images: Matrices, Spectra, and Filtering describes the deblurring algorithms and techniques collectively known as spectral filtering methods, in which the singular value decomposition—or a similar decomposition with spectral properties—is used to introduce the necessary regularization or filtering in the reconstructed image. The concise MATLAB® implementations described in the book provide a template of techniques that can be used to restore blurred images from many applications. This book’s treatment of image deblurring is unique in two ways: it includes algorithmic and implementation details; and by keeping the formulations in terms of matrices, vectors, and matrix computations, it makes the material accessible to a wide range of readers. Students and researchers in engineering will gain an understanding of the linear algebra behind filtering methods, while readers in applied mathematics, numerical analysis, and computational science will be exposed to modern techniques to solve realistic large-scale problems in image processing. With a focus on practical and efficient algorithms, Deblurring Images: Matrices, Spectra, and Filtering includes many examples, sample image data, and MATLAB codes that allow readers to experiment with the algorithms. It also incorporates introductory material, such as how to manipulate images within the MATLAB environment, making it a stand-alone text. Pointers to the literature are given for techniques not covered in the book. Audience This book is intended for beginners in the field of image restoration and regularization. Readers should be familiar with basic concepts of linear algebra and matrix computations, including the singular value decomposition and orthogonal transformations. A background in signal processing and a familiarity with regularization methods or with ill-posed problems are not needed. For readers who already have this knowledge, this book gives a new and practical perspective on the use of regularization methods to solve real problems. Preface; How to Get the Software; List of Symbols; Chapter 1: The Image Deblurring Problem; Chapter 2: Manipulating Images in MATLAB; Chapter 3: The Blurring Function; Chapter 4: Structured Matrix Computations; Chapter 5: SVD and Spectral Analysis; Chapter 6: Regularization by Spectral Filtering; Chapter 7: Color Images, Smoothing Norms, and Other Topics; Appendix: MATLAB Functions; Bibliography; Index

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值